Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/fmind/agent-docs/gather-agent-docsnpx skills add fmind/agent-docs --skill gather-agent-docsgit clone --depth 1 https://github.com/fmind/agent-docsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00088 | $0.01613 |
| Opus 5 | $0.00044 | $0.00807 |
| Sonnet 5 | $0.00018 | $0.00323 |
| Haiku 4.5 | $0.00009 | $0.00161 |
Grade A, and why
gather-agent-docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gather Agent Docs
Build a small, durable, agent-readable doc set for the project's key topics. Navigation map first, captured detail on request — future agents read the local map to land on the right upstream URL in one hop, then fetch upstream when they need depth.
Output layout
Use kebab-case slugs for topic directories (gemini-cli, cloud-run, firebase-app-hosting):
.agents/docs/
INDEX.md # one-line entry per topic, pointing to its DOC.md
<topic>/
DOC.md # entry point: summary, key concepts, documentation map, optional patterns
<SUBTOPIC>.md # optional deep dive (rare — see below)
Frontmatter
DOC.md and every <SUBTOPIC>.md open with YAML frontmatter the other skills key off:
---
last_verified: 2026-05-08 # required, ISO date
upstream_commit: <sha> # optional; commit at verification — enables smart refresh
sources: # required, at least one URL; richer set = more refresh short-circuits
docs: https://... # main documentation page
repo: https://github.com/... # source repository
changelog: https://... # changelog / release-notes — enables smart refresh
release: https://github.com/.../releases
---
INDEX.md carries last_verified only — set to the oldest date among topic files.
What each DOC.md contains
- Summary — one paragraph: what the topic is and where it fits.
- Key concepts — the primitives an agent needs, one terse line each. No config snippets, no flag tables.
- Documentation map — structured list of upstream pages, grouped by upstream nav section. Each entry:
[Page title](url) — one-line hook on what's there. - Patterns (optional, deepen-only) — paste-ready snippets for surfaces agents reach for repeatedly. Capped at ~5. Each block ends with an inline
_Source: …_link to the upstream anchor that backs it. - Subtopics (optional) — list sibling files with a one-line hook each.
Soft cap: ~100 lines for DOC.md, ~150 for a subtopic deep-dive.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 112 lines · 88 tokens per session scan A 7c89a2721697
gather-agent-docs is a skill published in the GitHub repository fmind/agent-docs (3 stars, last pushed 3mo ago), licensed MIT. It adds 88 tokens to every session and 1,613 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…
cupynumeric-migration-readiness
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment…